A method combining labeled and unlabeled data enhances sound source detection.
― 5 min read
Computer Science - Sound
RSSDiscover how audio cues aid players in table tennis.
― 6 min read
A system prioritizing melody while offering control over orchestral music generation.
― 5 min read
A new method uses virtual shadowing to enhance language learners' pronunciation feedback.
― 6 min read
New methods improve binaural audio quality in challenging sound environments.
― 8 min read
A new ASR method helps technology understand children's speech better.
― 5 min read
Composer uses text prompts to create complex music compositions in MIDI format.
― 5 min read
A resource for studying singing patterns in Japanese idol music.
― 6 min read
ViolinDiff enhances the realism of computer-generated violin music.
― 5 min read
Combining features enhances underwater sound classification accuracy.
― 6 min read
Transfer learning improves audio classification for underwater sound detection.
― 6 min read
A new model creates audio that matches video, enhancing media experiences.
― 4 min read
A method to boost automatic speech recognition by blending keyword lists with language models.
― 4 min read
A study on vocal imitation techniques using technology to enhance communication.
― 5 min read
Learn how to effectively train speech models with fewer labeled resources.
― 7 min read
An analysis of gender terminology in speech technology and its societal implications.
― 7 min read
A new framework improves detection of overlapping sound events in complex audio environments.
― 6 min read
Research on improving bird sound identification through machine learning techniques.
― 6 min read
A new method improves automatic piano cover creation using existing music transcription technology.
― 6 min read
A look at the Codec-SUPERB challenge results and codec performance metrics.
― 5 min read
MultiMed project enhances automatic speech recognition for better healthcare communication.
― 5 min read
A fresh approach to audio quality assessment without needing clean references.
― 6 min read
ECHO framework improves sound classification accuracy using structured labels and a two-stage learning process.
― 5 min read
New method enhances speech clarity by integrating visual information.
― 5 min read
A new approach enhances sound direction estimation for moving speakers in challenging settings.
― 8 min read
Audio Moment Retrieval enables pinpointing specific moments in long recordings.
― 5 min read
Safe Guard detects hate speech in real-time during voice interactions in social VR.
― 6 min read
AI is evolving to engage in more natural conversations.
― 5 min read
A novel approach uses real-time MRI to visualize speech production movements.
― 5 min read
A new method to detect early room reflections improves audio experiences.
― 6 min read
A project developing speech and text datasets for languages with limited resources.
― 5 min read
A new framework enhances voice recognition and adapts to various speech tasks.
― 4 min read
New methods are needed to detect advanced deepfake speech technologies.
― 5 min read
New methods boost accuracy in identifying animal sounds from limited data.
― 5 min read
New method improves virtual sound integration in AR environments.
― 6 min read
A new method aims to preserve voice privacy while allowing for effective communication.
― 4 min read
New methods improve speech recognition for low-resource languages without text.
― 4 min read
New methods enhance accuracy in speech recognition systems using phonetic understanding.
― 5 min read
This framework improves real-time animations by synchronizing speech and gestures seamlessly.
― 5 min read
New acoustic features enhance ASR systems' performance in noisy environments.
― 4 min read